Here we wanted to show the number of games being played by players to
quickly discuss this. We thought going with a 20 game minimum was the
best idea for analysis.
We did Principal Component Analysis to show if any variables stand out more than others.
We wanted to show with elbow plot that not many components were
really needed. Note we took out the “Entry Level Contract” type and
filtered that players must have played 20 games
We then wanted to see in the first two components what variables had
the most weight as this could help us in our reduction methods.
We wanted to show what the ridge plot looks like.
Also wanted to show the lasso plot.
Next, we wanted to show how all the models compared. We took the
linear regression model and compared it to ridge (which has an alpha
level of 0) and increased the alpha by every quartile until it got up to
1 (which is a lasso model). Here we wanted to show which model was the
best.
## 370 x 1 sparse Matrix of class "dgCMatrix"
## s0
## (Intercept) -2.745454e+06
## position .
## team .
## age 1.406116e+05
## x .
## ix_g60 .
## i_sh60 .
## i_cf60 .
## sf_percent .
## cf_percent .
## x_gf_percent .
## type 2.791848e+05
## expiry .
## shoots_catches -8.631687e+04
## skater_stats_power_play_goals .
## skater_stats_power_play_assists 1.539955e+04
## skater_stats_short_handed_goals .
## skater_stats_short_handed_assists .
## games_played .
## diff_other_x_goals_percentage .
## diff_other_corsi_percentage 4.645325e+04
## diff_all_x_goals_percentage 1.112594e+06
## diff_all_corsi_percentage 6.783054e+05
## diff_5on5_x_goals_percentage .
## diff_5on5_corsi_percentage .
## diff_4on5_x_goals_percentage .
## diff_4on5_corsi_percentage .
## diff_5on4_x_goals_percentage .
## diff_5on4_corsi_percentage .
## diff_other_x_on_goal .
## diff_other_x_goals .
## diff_other_shots_on_goal .
## diff_other_missed_shots .
## diff_other_blocked_shot_attempts .
## diff_other_shot_attempts .
## diff_other_goals .
## diff_other_rebounds .
## diff_other_rebound_goals 4.179019e+03
## diff_other_low_danger_shots .
## diff_other_medium_danger_shots .
## diff_other_high_danger_shots 1.076063e+04
## diff_other_low_dangerx_goals .
## diff_other_medium_dangerx_goals .
## diff_other_high_dangerx_goals .
## diff_other_low_danger_goals .
## diff_other_medium_danger_goals .
## diff_other_high_danger_goals .
## diff_other_unblocked_shot_attempts .
## diff_other_x_goals_fromx_rebounds_of_shots .
## diff_other_x_goals_from_actual_rebounds_of_shots .
## diff_other_reboundx_goals .
## diff_other_x_goals_with_earned_rebounds .
## diff_all_x_on_goal .
## diff_all_x_goals .
## diff_all_shots_on_goal .
## diff_all_missed_shots .
## diff_all_blocked_shot_attempts .
## diff_all_shot_attempts .
## diff_all_goals .
## diff_all_rebounds .
## diff_all_rebound_goals .
## diff_all_low_danger_shots .
## diff_all_medium_danger_shots .
## diff_all_high_danger_shots 8.235260e+02
## diff_all_low_dangerx_goals .
## diff_all_medium_dangerx_goals .
## diff_all_high_dangerx_goals .
## diff_all_low_danger_goals .
## diff_all_medium_danger_goals 8.208383e+02
## diff_all_high_danger_goals .
## diff_all_unblocked_shot_attempts .
## diff_all_x_goals_fromx_rebounds_of_shots .
## diff_all_x_goals_from_actual_rebounds_of_shots .
## diff_all_reboundx_goals .
## diff_all_x_goals_with_earned_rebounds .
## diff_5on5_x_on_goal .
## diff_5on5_x_goals .
## diff_5on5_shots_on_goal .
## diff_5on5_missed_shots .
## diff_5on5_blocked_shot_attempts .
## diff_5on5_shot_attempts .
## diff_5on5_goals .
## diff_5on5_rebounds .
## diff_5on5_rebound_goals -1.610453e+04
## diff_5on5_low_danger_shots .
## diff_5on5_medium_danger_shots .
## diff_5on5_high_danger_shots .
## diff_5on5_low_dangerx_goals .
## diff_5on5_medium_dangerx_goals .
## diff_5on5_high_dangerx_goals .
## diff_5on5_low_danger_goals -4.600502e+03
## diff_5on5_medium_danger_goals .
## diff_5on5_high_danger_goals .
## diff_5on5_unblocked_shot_attempts .
## diff_5on5_x_goals_fromx_rebounds_of_shots .
## diff_5on5_x_goals_from_actual_rebounds_of_shots .
## diff_5on5_reboundx_goals .
## diff_5on5_x_goals_with_earned_rebounds .
## diff_4on5_x_on_goal .
## diff_4on5_x_goals .
## diff_4on5_shots_on_goal .
## diff_4on5_missed_shots .
## diff_4on5_blocked_shot_attempts .
## diff_4on5_shot_attempts .
## diff_4on5_goals .
## diff_4on5_rebounds .
## diff_4on5_rebound_goals .
## diff_4on5_low_danger_shots .
## diff_4on5_medium_danger_shots .
## diff_4on5_high_danger_shots .
## diff_4on5_low_dangerx_goals .
## diff_4on5_medium_dangerx_goals .
## diff_4on5_high_dangerx_goals .
## diff_4on5_low_danger_goals .
## diff_4on5_medium_danger_goals .
## diff_4on5_high_danger_goals .
## diff_4on5_unblocked_shot_attempts .
## diff_4on5_x_goals_fromx_rebounds_of_shots .
## diff_4on5_x_goals_from_actual_rebounds_of_shots .
## diff_4on5_reboundx_goals .
## diff_4on5_x_goals_with_earned_rebounds .
## diff_5on4_x_on_goal .
## diff_5on4_x_goals .
## diff_5on4_shots_on_goal .
## diff_5on4_missed_shots .
## diff_5on4_blocked_shot_attempts .
## diff_5on4_shot_attempts .
## diff_5on4_goals .
## diff_5on4_rebounds .
## diff_5on4_rebound_goals 3.977725e+04
## diff_5on4_low_danger_shots .
## diff_5on4_medium_danger_shots .
## diff_5on4_high_danger_shots .
## diff_5on4_low_dangerx_goals .
## diff_5on4_medium_dangerx_goals .
## diff_5on4_high_dangerx_goals .
## diff_5on4_low_danger_goals .
## diff_5on4_medium_danger_goals .
## diff_5on4_high_danger_goals .
## diff_5on4_unblocked_shot_attempts .
## diff_5on4_x_goals_fromx_rebounds_of_shots 8.106352e+04
## diff_5on4_x_goals_from_actual_rebounds_of_shots 1.484678e+04
## diff_5on4_reboundx_goals 3.403994e+04
## diff_5on4_x_goals_with_earned_rebounds .
## other_icetime .
## all_icetime .
## x5on5_icetime .
## x4on5_icetime .
## x5on4_icetime .
## other_i_f_x_on_goal .
## all_i_f_x_on_goal .
## x5on5_i_f_x_on_goal .
## x4on5_i_f_x_on_goal .
## x5on4_i_f_x_on_goal .
## other_i_f_x_goals .
## all_i_f_x_goals .
## x5on5_i_f_x_goals .
## x4on5_i_f_x_goals .
## x5on4_i_f_x_goals .
## other_i_f_x_rebounds 2.388166e+04
## all_i_f_x_rebounds .
## x5on5_i_f_x_rebounds .
## x4on5_i_f_x_rebounds .
## x5on4_i_f_x_rebounds .
## other_i_f_x_play_continued_in_zone .
## all_i_f_x_play_continued_in_zone .
## x5on5_i_f_x_play_continued_in_zone .
## x4on5_i_f_x_play_continued_in_zone .
## x5on4_i_f_x_play_continued_in_zone .
## other_i_f_x_play_continued_outside_zone .
## all_i_f_x_play_continued_outside_zone .
## x5on5_i_f_x_play_continued_outside_zone .
## x4on5_i_f_x_play_continued_outside_zone .
## x5on4_i_f_x_play_continued_outside_zone .
## other_i_f_primary_assists .
## all_i_f_primary_assists 8.250216e+03
## x5on5_i_f_primary_assists .
## x4on5_i_f_primary_assists .
## x5on4_i_f_primary_assists .
## other_i_f_secondary_assists .
## all_i_f_secondary_assists 1.615344e+04
## x5on5_i_f_secondary_assists .
## x4on5_i_f_secondary_assists -1.280227e+05
## x5on4_i_f_secondary_assists .
## other_i_f_shots_on_goal .
## all_i_f_shots_on_goal .
## x5on5_i_f_shots_on_goal .
## x4on5_i_f_shots_on_goal .
## x5on4_i_f_shots_on_goal .
## other_i_f_missed_shots .
## all_i_f_missed_shots .
## x5on5_i_f_missed_shots .
## x4on5_i_f_missed_shots .
## x5on4_i_f_missed_shots .
## other_i_f_blocked_shot_attempts .
## all_i_f_blocked_shot_attempts .
## x5on5_i_f_blocked_shot_attempts .
## x4on5_i_f_blocked_shot_attempts -1.586253e+04
## x5on4_i_f_blocked_shot_attempts .
## other_i_f_shot_attempts .
## all_i_f_shot_attempts .
## x5on5_i_f_shot_attempts .
## x4on5_i_f_shot_attempts .
## x5on4_i_f_shot_attempts .
## other_i_f_points .
## all_i_f_points .
## x5on5_i_f_points .
## x4on5_i_f_points .
## x5on4_i_f_points .
## other_i_f_goals .
## all_i_f_goals .
## x5on5_i_f_goals .
## x4on5_i_f_goals .
## x5on4_i_f_goals .
## other_i_f_rebounds .
## all_i_f_rebounds .
## x5on5_i_f_rebounds .
## x4on5_i_f_rebounds .
## x5on4_i_f_rebounds .
## other_i_f_rebound_goals .
## all_i_f_rebound_goals .
## x5on5_i_f_rebound_goals .
## x4on5_i_f_rebound_goals .
## x5on4_i_f_rebound_goals .
## other_i_f_play_continued_in_zone .
## all_i_f_play_continued_in_zone .
## x5on5_i_f_play_continued_in_zone .
## x4on5_i_f_play_continued_in_zone .
## x5on4_i_f_play_continued_in_zone 5.671506e+04
## other_i_f_play_continued_outside_zone 3.676679e+04
## all_i_f_play_continued_outside_zone .
## x5on5_i_f_play_continued_outside_zone .
## x4on5_i_f_play_continued_outside_zone .
## x5on4_i_f_play_continued_outside_zone .
## other_i_f_saved_shots_on_goal .
## all_i_f_saved_shots_on_goal .
## x5on5_i_f_saved_shots_on_goal .
## x4on5_i_f_saved_shots_on_goal .
## x5on4_i_f_saved_shots_on_goal .
## other_i_f_hits 2.609656e+03
## all_i_f_hits .
## x5on5_i_f_hits .
## x4on5_i_f_hits .
## x5on4_i_f_hits .
## other_i_f_takeaways 6.799045e+04
## all_i_f_takeaways .
## x5on5_i_f_takeaways 1.546996e+04
## x4on5_i_f_takeaways .
## x5on4_i_f_takeaways .
## other_i_f_giveaways .
## all_i_f_giveaways 2.992792e+03
## x5on5_i_f_giveaways 7.304789e+03
## x4on5_i_f_giveaways .
## x5on4_i_f_giveaways .
## other_i_f_low_danger_shots .
## all_i_f_low_danger_shots .
## x5on5_i_f_low_danger_shots .
## x4on5_i_f_low_danger_shots .
## x5on4_i_f_low_danger_shots .
## other_i_f_medium_danger_shots .
## all_i_f_medium_danger_shots .
## x5on5_i_f_medium_danger_shots .
## x4on5_i_f_medium_danger_shots .
## x5on4_i_f_medium_danger_shots .
## other_i_f_high_danger_shots .
## all_i_f_high_danger_shots .
## x5on5_i_f_high_danger_shots .
## x4on5_i_f_high_danger_shots -1.968148e+04
## x5on4_i_f_high_danger_shots .
## other_i_f_low_dangerx_goals .
## all_i_f_low_dangerx_goals .
## x5on5_i_f_low_dangerx_goals .
## x4on5_i_f_low_dangerx_goals .
## x5on4_i_f_low_dangerx_goals .
## other_i_f_medium_dangerx_goals .
## all_i_f_medium_dangerx_goals .
## x5on5_i_f_medium_dangerx_goals .
## x4on5_i_f_medium_dangerx_goals .
## x5on4_i_f_medium_dangerx_goals .
## other_i_f_high_dangerx_goals .
## all_i_f_high_dangerx_goals .
## x5on5_i_f_high_dangerx_goals .
## x4on5_i_f_high_dangerx_goals .
## x5on4_i_f_high_dangerx_goals .
## other_i_f_low_danger_goals .
## all_i_f_low_danger_goals .
## x5on5_i_f_low_danger_goals .
## x4on5_i_f_low_danger_goals -3.318223e+05
## x5on4_i_f_low_danger_goals .
## other_i_f_medium_danger_goals .
## all_i_f_medium_danger_goals .
## x5on5_i_f_medium_danger_goals .
## x4on5_i_f_medium_danger_goals -1.499102e+04
## x5on4_i_f_medium_danger_goals .
## other_i_f_high_danger_goals .
## all_i_f_high_danger_goals .
## x5on5_i_f_high_danger_goals .
## x4on5_i_f_high_danger_goals .
## x5on4_i_f_high_danger_goals .
## other_i_f_unblocked_shot_attempts .
## all_i_f_unblocked_shot_attempts .
## x5on5_i_f_unblocked_shot_attempts .
## x4on5_i_f_unblocked_shot_attempts .
## x5on4_i_f_unblocked_shot_attempts .
## other_i_f_d_zone_giveaways 7.575754e+04
## all_i_f_d_zone_giveaways .
## x5on5_i_f_d_zone_giveaways .
## x4on5_i_f_d_zone_giveaways .
## x5on4_i_f_d_zone_giveaways .
## other_i_f_x_goals_fromx_rebounds_of_shots 4.330224e+04
## all_i_f_x_goals_fromx_rebounds_of_shots .
## x5on5_i_f_x_goals_fromx_rebounds_of_shots .
## x4on5_i_f_x_goals_fromx_rebounds_of_shots .
## x5on4_i_f_x_goals_fromx_rebounds_of_shots .
## other_i_f_x_goals_from_actual_rebounds_of_shots .
## all_i_f_x_goals_from_actual_rebounds_of_shots .
## x5on5_i_f_x_goals_from_actual_rebounds_of_shots .
## x4on5_i_f_x_goals_from_actual_rebounds_of_shots .
## x5on4_i_f_x_goals_from_actual_rebounds_of_shots .
## other_i_f_reboundx_goals .
## all_i_f_reboundx_goals .
## x5on5_i_f_reboundx_goals .
## x4on5_i_f_reboundx_goals -8.308048e+04
## x5on4_i_f_reboundx_goals .
## other_i_f_o_zone_shift_ends .
## all_i_f_o_zone_shift_ends .
## x5on5_i_f_o_zone_shift_ends .
## x4on5_i_f_o_zone_shift_ends .
## x5on4_i_f_o_zone_shift_ends .
## other_i_f_d_zone_shift_ends .
## all_i_f_d_zone_shift_ends .
## x5on5_i_f_d_zone_shift_ends .
## x4on5_i_f_d_zone_shift_ends .
## x5on4_i_f_d_zone_shift_ends .
## other_i_f_neutral_zone_shift_ends 4.345798e+04
## all_i_f_neutral_zone_shift_ends .
## x5on5_i_f_neutral_zone_shift_ends .
## x4on5_i_f_neutral_zone_shift_ends .
## x5on4_i_f_neutral_zone_shift_ends .
## other_faceoffs_won .
## all_faceoffs_won .
## x5on5_faceoffs_won .
## x4on5_faceoffs_won .
## x5on4_faceoffs_won 2.215846e+03
## other_faceoffs_lost .
## all_faceoffs_lost .
## x5on5_faceoffs_lost .
## x4on5_faceoffs_lost .
## x5on4_faceoffs_lost .
## other_time_on_bench .
## all_time_on_bench -5.327350e+00
## x5on5_time_on_bench .
## x4on5_time_on_bench .
## x5on4_time_on_bench .
## other_shots_blocked_by_player .
## all_shots_blocked_by_player .
## x5on5_shots_blocked_by_player .
## x4on5_shots_blocked_by_player -5.215833e+04
## x5on4_shots_blocked_by_player .
## other_diff_number_of_penalty .
## all_diff_number_of_penalty .
## x5on5_diff_number_of_penalty .
## x4on5_diff_number_of_penalty 3.223018e+03
## x5on4_diff_number_of_penalty .
## other_diff_penalty_minutes .
## all_diff_penalty_minutes .
## x5on5_diff_penalty_minutes .
## x4on5_diff_penalty_minutes .
## x5on4_diff_penalty_minutes .
## test_fold .
## 370 x 1 sparse Matrix of class "dgCMatrix"
## s0
## (Intercept) -2.267918e+06
## position .
## team 6.885255e+03
## age 1.121365e+05
## x .
## ix_g60 .
## i_sh60 .
## i_cf60 .
## sf_percent .
## cf_percent .
## x_gf_percent .
## type 2.620432e+05
## expiry 8.224642e+04
## shoots_catches .
## skater_stats_power_play_goals .
## skater_stats_power_play_assists .
## skater_stats_short_handed_goals .
## skater_stats_short_handed_assists .
## games_played .
## diff_other_x_goals_percentage .
## diff_other_corsi_percentage .
## diff_all_x_goals_percentage .
## diff_all_corsi_percentage .
## diff_5on5_x_goals_percentage .
## diff_5on5_corsi_percentage 3.892032e+06
## diff_4on5_x_goals_percentage .
## diff_4on5_corsi_percentage .
## diff_5on4_x_goals_percentage .
## diff_5on4_corsi_percentage .
## diff_other_x_on_goal .
## diff_other_x_goals .
## diff_other_shots_on_goal .
## diff_other_missed_shots -4.915081e+03
## diff_other_blocked_shot_attempts .
## diff_other_shot_attempts .
## diff_other_goals .
## diff_other_rebounds .
## diff_other_rebound_goals .
## diff_other_low_danger_shots .
## diff_other_medium_danger_shots .
## diff_other_high_danger_shots .
## diff_other_low_dangerx_goals .
## diff_other_medium_dangerx_goals .
## diff_other_high_dangerx_goals .
## diff_other_low_danger_goals -1.423014e+05
## diff_other_medium_danger_goals -1.590961e+04
## diff_other_high_danger_goals .
## diff_other_unblocked_shot_attempts .
## diff_other_x_goals_fromx_rebounds_of_shots .
## diff_other_x_goals_from_actual_rebounds_of_shots .
## diff_other_reboundx_goals .
## diff_other_x_goals_with_earned_rebounds .
## diff_all_x_on_goal .
## diff_all_x_goals .
## diff_all_shots_on_goal .
## diff_all_missed_shots .
## diff_all_blocked_shot_attempts .
## diff_all_shot_attempts .
## diff_all_goals .
## diff_all_rebounds .
## diff_all_rebound_goals .
## diff_all_low_danger_shots .
## diff_all_medium_danger_shots .
## diff_all_high_danger_shots .
## diff_all_low_dangerx_goals .
## diff_all_medium_dangerx_goals .
## diff_all_high_dangerx_goals .
## diff_all_low_danger_goals .
## diff_all_medium_danger_goals .
## diff_all_high_danger_goals .
## diff_all_unblocked_shot_attempts .
## diff_all_x_goals_fromx_rebounds_of_shots .
## diff_all_x_goals_from_actual_rebounds_of_shots .
## diff_all_reboundx_goals .
## diff_all_x_goals_with_earned_rebounds .
## diff_5on5_x_on_goal .
## diff_5on5_x_goals .
## diff_5on5_shots_on_goal .
## diff_5on5_missed_shots .
## diff_5on5_blocked_shot_attempts .
## diff_5on5_shot_attempts .
## diff_5on5_goals .
## diff_5on5_rebounds .
## diff_5on5_rebound_goals -9.478278e+01
## diff_5on5_low_danger_shots .
## diff_5on5_medium_danger_shots .
## diff_5on5_high_danger_shots .
## diff_5on5_low_dangerx_goals .
## diff_5on5_medium_dangerx_goals .
## diff_5on5_high_dangerx_goals .
## diff_5on5_low_danger_goals 1.365129e+04
## diff_5on5_medium_danger_goals .
## diff_5on5_high_danger_goals .
## diff_5on5_unblocked_shot_attempts .
## diff_5on5_x_goals_fromx_rebounds_of_shots .
## diff_5on5_x_goals_from_actual_rebounds_of_shots .
## diff_5on5_reboundx_goals .
## diff_5on5_x_goals_with_earned_rebounds .
## diff_4on5_x_on_goal .
## diff_4on5_x_goals .
## diff_4on5_shots_on_goal .
## diff_4on5_missed_shots .
## diff_4on5_blocked_shot_attempts .
## diff_4on5_shot_attempts .
## diff_4on5_goals .
## diff_4on5_rebounds .
## diff_4on5_rebound_goals .
## diff_4on5_low_danger_shots .
## diff_4on5_medium_danger_shots .
## diff_4on5_high_danger_shots .
## diff_4on5_low_dangerx_goals .
## diff_4on5_medium_dangerx_goals .
## diff_4on5_high_dangerx_goals .
## diff_4on5_low_danger_goals .
## diff_4on5_medium_danger_goals .
## diff_4on5_high_danger_goals .
## diff_4on5_unblocked_shot_attempts .
## diff_4on5_x_goals_fromx_rebounds_of_shots .
## diff_4on5_x_goals_from_actual_rebounds_of_shots .
## diff_4on5_reboundx_goals .
## diff_4on5_x_goals_with_earned_rebounds .
## diff_5on4_x_on_goal .
## diff_5on4_x_goals .
## diff_5on4_shots_on_goal .
## diff_5on4_missed_shots 4.687439e+02
## diff_5on4_blocked_shot_attempts 4.044663e+02
## diff_5on4_shot_attempts .
## diff_5on4_goals .
## diff_5on4_rebounds 3.144132e+02
## diff_5on4_rebound_goals .
## diff_5on4_low_danger_shots .
## diff_5on4_medium_danger_shots .
## diff_5on4_high_danger_shots .
## diff_5on4_low_dangerx_goals .
## diff_5on4_medium_dangerx_goals .
## diff_5on4_high_dangerx_goals .
## diff_5on4_low_danger_goals 4.544523e+04
## diff_5on4_medium_danger_goals .
## diff_5on4_high_danger_goals .
## diff_5on4_unblocked_shot_attempts .
## diff_5on4_x_goals_fromx_rebounds_of_shots .
## diff_5on4_x_goals_from_actual_rebounds_of_shots .
## diff_5on4_reboundx_goals .
## diff_5on4_x_goals_with_earned_rebounds .
## other_icetime 3.243593e+02
## all_icetime .
## x5on5_icetime .
## x4on5_icetime .
## x5on4_icetime .
## other_i_f_x_on_goal .
## all_i_f_x_on_goal .
## x5on5_i_f_x_on_goal .
## x4on5_i_f_x_on_goal .
## x5on4_i_f_x_on_goal .
## other_i_f_x_goals .
## all_i_f_x_goals .
## x5on5_i_f_x_goals .
## x4on5_i_f_x_goals .
## x5on4_i_f_x_goals .
## other_i_f_x_rebounds .
## all_i_f_x_rebounds .
## x5on5_i_f_x_rebounds .
## x4on5_i_f_x_rebounds .
## x5on4_i_f_x_rebounds .
## other_i_f_x_play_continued_in_zone .
## all_i_f_x_play_continued_in_zone .
## x5on5_i_f_x_play_continued_in_zone .
## x4on5_i_f_x_play_continued_in_zone .
## x5on4_i_f_x_play_continued_in_zone .
## other_i_f_x_play_continued_outside_zone .
## all_i_f_x_play_continued_outside_zone .
## x5on5_i_f_x_play_continued_outside_zone .
## x4on5_i_f_x_play_continued_outside_zone .
## x5on4_i_f_x_play_continued_outside_zone .
## other_i_f_primary_assists .
## all_i_f_primary_assists .
## x5on5_i_f_primary_assists .
## x4on5_i_f_primary_assists .
## x5on4_i_f_primary_assists .
## other_i_f_secondary_assists .
## all_i_f_secondary_assists .
## x5on5_i_f_secondary_assists .
## x4on5_i_f_secondary_assists .
## x5on4_i_f_secondary_assists .
## other_i_f_shots_on_goal .
## all_i_f_shots_on_goal .
## x5on5_i_f_shots_on_goal .
## x4on5_i_f_shots_on_goal .
## x5on4_i_f_shots_on_goal .
## other_i_f_missed_shots .
## all_i_f_missed_shots .
## x5on5_i_f_missed_shots .
## x4on5_i_f_missed_shots .
## x5on4_i_f_missed_shots .
## other_i_f_blocked_shot_attempts 2.357443e+04
## all_i_f_blocked_shot_attempts .
## x5on5_i_f_blocked_shot_attempts .
## x4on5_i_f_blocked_shot_attempts .
## x5on4_i_f_blocked_shot_attempts 7.309181e+03
## other_i_f_shot_attempts .
## all_i_f_shot_attempts .
## x5on5_i_f_shot_attempts .
## x4on5_i_f_shot_attempts .
## x5on4_i_f_shot_attempts .
## other_i_f_points .
## all_i_f_points .
## x5on5_i_f_points .
## x4on5_i_f_points .
## x5on4_i_f_points .
## other_i_f_goals .
## all_i_f_goals .
## x5on5_i_f_goals .
## x4on5_i_f_goals .
## x5on4_i_f_goals .
## other_i_f_rebounds .
## all_i_f_rebounds .
## x5on5_i_f_rebounds .
## x4on5_i_f_rebounds .
## x5on4_i_f_rebounds .
## other_i_f_rebound_goals .
## all_i_f_rebound_goals .
## x5on5_i_f_rebound_goals .
## x4on5_i_f_rebound_goals .
## x5on4_i_f_rebound_goals .
## other_i_f_play_continued_in_zone .
## all_i_f_play_continued_in_zone .
## x5on5_i_f_play_continued_in_zone .
## x4on5_i_f_play_continued_in_zone .
## x5on4_i_f_play_continued_in_zone .
## other_i_f_play_continued_outside_zone .
## all_i_f_play_continued_outside_zone 1.633282e+04
## x5on5_i_f_play_continued_outside_zone .
## x4on5_i_f_play_continued_outside_zone 7.579989e+03
## x5on4_i_f_play_continued_outside_zone .
## other_i_f_saved_shots_on_goal .
## all_i_f_saved_shots_on_goal .
## x5on5_i_f_saved_shots_on_goal .
## x4on5_i_f_saved_shots_on_goal .
## x5on4_i_f_saved_shots_on_goal .
## other_i_f_hits .
## all_i_f_hits .
## x5on5_i_f_hits .
## x4on5_i_f_hits .
## x5on4_i_f_hits .
## other_i_f_takeaways .
## all_i_f_takeaways .
## x5on5_i_f_takeaways .
## x4on5_i_f_takeaways .
## x5on4_i_f_takeaways .
## other_i_f_giveaways 2.186179e+04
## all_i_f_giveaways .
## x5on5_i_f_giveaways .
## x4on5_i_f_giveaways .
## x5on4_i_f_giveaways .
## other_i_f_low_danger_shots .
## all_i_f_low_danger_shots .
## x5on5_i_f_low_danger_shots .
## x4on5_i_f_low_danger_shots .
## x5on4_i_f_low_danger_shots .
## other_i_f_medium_danger_shots .
## all_i_f_medium_danger_shots 2.315194e+03
## x5on5_i_f_medium_danger_shots .
## x4on5_i_f_medium_danger_shots .
## x5on4_i_f_medium_danger_shots .
## other_i_f_high_danger_shots .
## all_i_f_high_danger_shots .
## x5on5_i_f_high_danger_shots .
## x4on5_i_f_high_danger_shots .
## x5on4_i_f_high_danger_shots .
## other_i_f_low_dangerx_goals .
## all_i_f_low_dangerx_goals .
## x5on5_i_f_low_dangerx_goals .
## x4on5_i_f_low_dangerx_goals .
## x5on4_i_f_low_dangerx_goals .
## other_i_f_medium_dangerx_goals .
## all_i_f_medium_dangerx_goals 4.220355e+05
## x5on5_i_f_medium_dangerx_goals .
## x4on5_i_f_medium_dangerx_goals .
## x5on4_i_f_medium_dangerx_goals .
## other_i_f_high_dangerx_goals .
## all_i_f_high_dangerx_goals .
## x5on5_i_f_high_dangerx_goals .
## x4on5_i_f_high_dangerx_goals .
## x5on4_i_f_high_dangerx_goals .
## other_i_f_low_danger_goals .
## all_i_f_low_danger_goals .
## x5on5_i_f_low_danger_goals .
## x4on5_i_f_low_danger_goals .
## x5on4_i_f_low_danger_goals .
## other_i_f_medium_danger_goals .
## all_i_f_medium_danger_goals .
## x5on5_i_f_medium_danger_goals .
## x4on5_i_f_medium_danger_goals -5.817501e+05
## x5on4_i_f_medium_danger_goals .
## other_i_f_high_danger_goals .
## all_i_f_high_danger_goals .
## x5on5_i_f_high_danger_goals .
## x4on5_i_f_high_danger_goals .
## x5on4_i_f_high_danger_goals .
## other_i_f_unblocked_shot_attempts .
## all_i_f_unblocked_shot_attempts .
## x5on5_i_f_unblocked_shot_attempts .
## x4on5_i_f_unblocked_shot_attempts .
## x5on4_i_f_unblocked_shot_attempts .
## other_i_f_d_zone_giveaways .
## all_i_f_d_zone_giveaways .
## x5on5_i_f_d_zone_giveaways .
## x4on5_i_f_d_zone_giveaways .
## x5on4_i_f_d_zone_giveaways .
## other_i_f_x_goals_fromx_rebounds_of_shots .
## all_i_f_x_goals_fromx_rebounds_of_shots .
## x5on5_i_f_x_goals_fromx_rebounds_of_shots .
## x4on5_i_f_x_goals_fromx_rebounds_of_shots .
## x5on4_i_f_x_goals_fromx_rebounds_of_shots .
## other_i_f_x_goals_from_actual_rebounds_of_shots .
## all_i_f_x_goals_from_actual_rebounds_of_shots .
## x5on5_i_f_x_goals_from_actual_rebounds_of_shots .
## x4on5_i_f_x_goals_from_actual_rebounds_of_shots .
## x5on4_i_f_x_goals_from_actual_rebounds_of_shots .
## other_i_f_reboundx_goals 1.504252e+05
## all_i_f_reboundx_goals .
## x5on5_i_f_reboundx_goals .
## x4on5_i_f_reboundx_goals 2.761572e+05
## x5on4_i_f_reboundx_goals .
## other_i_f_o_zone_shift_ends .
## all_i_f_o_zone_shift_ends .
## x5on5_i_f_o_zone_shift_ends .
## x4on5_i_f_o_zone_shift_ends .
## x5on4_i_f_o_zone_shift_ends .
## other_i_f_d_zone_shift_ends .
## all_i_f_d_zone_shift_ends .
## x5on5_i_f_d_zone_shift_ends .
## x4on5_i_f_d_zone_shift_ends .
## x5on4_i_f_d_zone_shift_ends 1.834465e+04
## other_i_f_neutral_zone_shift_ends 3.054726e+04
## all_i_f_neutral_zone_shift_ends .
## x5on5_i_f_neutral_zone_shift_ends .
## x4on5_i_f_neutral_zone_shift_ends .
## x5on4_i_f_neutral_zone_shift_ends .
## other_faceoffs_won .
## all_faceoffs_won .
## x5on5_faceoffs_won .
## x4on5_faceoffs_won .
## x5on4_faceoffs_won .
## other_faceoffs_lost .
## all_faceoffs_lost .
## x5on5_faceoffs_lost .
## x4on5_faceoffs_lost .
## x5on4_faceoffs_lost .
## other_time_on_bench .
## all_time_on_bench -8.429820e+00
## x5on5_time_on_bench .
## x4on5_time_on_bench .
## x5on4_time_on_bench .
## other_shots_blocked_by_player .
## all_shots_blocked_by_player .
## x5on5_shots_blocked_by_player .
## x4on5_shots_blocked_by_player .
## x5on4_shots_blocked_by_player .
## other_diff_number_of_penalty .
## all_diff_number_of_penalty .
## x5on5_diff_number_of_penalty .
## x4on5_diff_number_of_penalty .
## x5on4_diff_number_of_penalty .
## other_diff_penalty_minutes .
## all_diff_penalty_minutes .
## x5on5_diff_penalty_minutes .
## x4on5_diff_penalty_minutes .
## x5on4_diff_penalty_minutes .
## test_fold .
Here we wanted to show a plot of the top 100 most important variables in this type of dimension reduction technique.
## Ranger result
##
## Call:
## ranger(cap_hit ~ ., salary21Subset, importance = "impurity", mtry = ncol(salary21Subset)/3)
##
## Type: Regression
## Number of trees: 500
## Sample size: 663
## Number of independent variables: 369
## Mtry: 123
## Target node size: 5
## Variable importance mode: impurity
## Splitrule: variance
## OOB prediction error (MSE): 2.354971e+12
## R squared (OOB): 0.6527016
We did the same thing subsetting the data by forwards.
## Ranger result
##
## Call:
## ranger(cap_hit ~ ., salary21SubsetForward, importance = "impurity", num.trees = 400, mtry = ncol(salary21SubsetForward)/3)
##
## Type: Regression
## Number of trees: 400
## Sample size: 447
## Number of independent variables: 368
## Mtry: 123
## Target node size: 5
## Variable importance mode: impurity
## Splitrule: variance
## OOB prediction error (MSE): 2.460151e+12
## R squared (OOB): 0.6572097
And lastly did the same random forest technique subsetting it by defense.
## Ranger result
##
## Call:
## ranger(cap_hit ~ ., salary21SubsetDefense, importance = "impurity", num.trees = 400, mtry = ncol(salary21SubsetDefense)/3)
##
## Type: Regression
## Number of trees: 400
## Sample size: 216
## Number of independent variables: 368
## Mtry: 123
## Target node size: 5
## Variable importance mode: impurity
## Splitrule: variance
## OOB prediction error (MSE): 2.597281e+12
## R squared (OOB): 0.5661637
By having these different plots, we tried to see if we could find a pattern somewhere that would give us the most important variables to use in our reduction.
We first looked at the all data, without subsetting by position.
## # A tibble: 132 × 2
## value n
## <chr> <int>
## 1 age 2
## 2 all_i_f_primary_assists 2
## 3 all_i_f_secondary_assists 2
## 4 all_time_on_bench 2
## 5 diff_5on4_rebound_goals 2
## 6 diff_all_high_danger_shots 2
## 7 diff_other_low_danger_goals 2
## 8 expiry 2
## 9 other_i_f_neutral_zone_shift_ends 2
## 10 other_i_f_play_continued_outside_zone 2
## # … with 122 more rows
We then did the same doing by forwards.
## # A tibble: 121 × 2
## value n
## <chr> <int>
## 1 age 2
## 2 all_i_f_giveaways 2
## 3 all_i_f_primary_assists 2
## 4 all_i_f_secondary_assists 2
## 5 all_time_on_bench 2
## 6 diff_5on4_rebound_goals 2
## 7 diff_5on4_reboundx_goals 2
## 8 diff_5on4_x_goals_from_actual_rebounds_of_shots 2
## 9 diff_5on4_x_goals_fromx_rebounds_of_shots 2
## 10 diff_all_high_danger_shots 2
## # … with 111 more rows
And lastly looked at the defensive players.
## # A tibble: 127 × 2
## value n
## <chr> <int>
## 1 age 2
## 2 all_i_f_primary_assists 2
## 3 all_i_f_secondary_assists 2
## 4 all_time_on_bench 2
## 5 diff_5on4_x_goals_from_actual_rebounds_of_shots 2
## 6 diff_all_corsi_percentage 2
## 7 diff_other_high_danger_shots 2
## 8 other_i_f_neutral_zone_shift_ends 2
## 9 other_i_f_x_goals_fromx_rebounds_of_shots 2
## 10 other_i_f_x_rebounds 2
## # … with 117 more rows
By using random forest, we could look at what the model says is the
optimal number of predictors we should end up using.